多层感知器( Multi-Layer Perceptron,MLP ),本质上为为“输入层—隐藏层—输出层”的单隐层神经网络。MLP可以视为一种输入变量经过一次非线性变换的特殊Logistic回归。单隐层足以使MLP成为通用费雷器。
模型
MLP的通用结构如下:
MLP的输出函数可以标示为
其中,隐层的表达式为
其中可以用多种函数表示,典型的包括和函数:
为了训练MLP模型,使用前馈算法对对所有函数进行求导,
用Theano实现MLP
实现隐层类
class HiddenLayer(object):
def __init__(self, rng, input, n_in, n_out, W=None, b=None,
activation=T.tanh):
"""
Typical hidden layer of a MLP: units are fully-connected and have
sigmoidal activation function. Weight matrix W is of shape (n_in,n_out)
and the bias vector b is of shape (n_out,).
NOTE : The nonlinearity used here is tanh
Hidden unit activation is given by: tanh(dot(input,W) + b)
:type rng: numpy.random.RandomState
:param rng: a random number generator used to initialize weights
:type input: theano.tensor.dmatrix
:param input: a symbolic tensor of shape (n_examples, n_in)
:type n_in: int
:param n_in: dimensionality of input
:type n_out: int
:param n_out: number of hidden units
:type activation: theano.Op or function
:param activation: Non linearity to be applied in the hidden
layer
"""
self.input = input
# `W` is initialized with `W_values` which is uniformely sampled
# from sqrt(-6./(n_in+n_hidden)) and sqrt(6./(n_in+n_hidden))
# for tanh activation function
# the output of uniform if converted using asarray to dtype
# theano.config.floatX so that the code is runable on GPU
# Note : optimal initialization of weights is dependent on the
# activation function used (among other things).
# For example, results presented in [Xavier10] suggest that you
# should use 4 times larger initial weights for sigmoid
# compared to tanh
# We have no info for other function, so we use the same as
# tanh.
if W is None:
W_values = numpy.asarray(
rng.uniform(
low=-numpy.sqrt(6. / (n_in + n_out)),
high=numpy.sqrt(6. / (n_in + n_out)),
size=(n_in, n_out)
),
dtype=theano.config.floatX
)
if activation == theano.tensor.nnet.sigmoid:
W_values *= 4
W = theano.shared(value=W_values, name='W', borrow=True)
if b is None:
b_values = numpy.zeros((n_out,), dtype=theano.config.floatX)
b = theano.shared(value=b_values, name='b', borrow=True)
self.W = W
self.b = b
lin_output = T.dot(input, self.W) + self.b
self.output = (
lin_output if activation is None
else activation(lin_output)
)
实现MLP类
class MLP(object):
"""Multi-Layer Perceptron Class
A multilayer perceptron is a feedforward artificial neural network model
that has one layer or more of hidden units and nonlinear activations.
Intermediate layers usually have as activation function tanh or the
sigmoid function (defined here by a ``HiddenLayer`` class) while the
top layer is a softmax layer (defined here by a ``LogisticRegression``
class).
"""
def __init__(self, rng, input, n_in, n_hidden, n_out):
"""Initialize the parameters for the multilayer perceptron
:type rng: numpy.random.RandomState
:param rng: a random number generator used to initialize weights
:type input: theano.tensor.TensorType
:param input: symbolic variable that describes the input of the
architecture (one minibatch)
:type n_in: int
:param n_in: number of input units, the dimension of the space in
which the datapoints lie
:type n_hidden: int
:param n_hidden: number of hidden units
:type n_out: int
:param n_out: number of output units, the dimension of the space in
which the labels lie
"""
# Since we are dealing with a one hidden layer MLP, this will translate
# into a HiddenLayer with a tanh activation function connected to the
# LogisticRegression layer; the activation function can be replaced by
# sigmoid or any other nonlinear function
self.hiddenLayer = HiddenLayer(
rng=rng,
input=input,
n_in=n_in,
n_out=n_hidden,
activation=T.tanh
)
# The logistic regression layer gets as input the hidden units
# of the hidden layer
self.logRegressionLayer = LogisticRegression(
input=self.hiddenLayer.output,
n_in=n_hidden,
n_out=n_out
)
# L1 norm ; one regularization option is to enforce L1 norm to
# be small
self.L1 = (
abs(self.hiddenLayer.W).sum()
+ abs(self.logRegressionLayer.W).sum()
)
# square of L2 norm ; one regularization option is to enforce
# square of L2 norm to be small
self.L2_sqr = (
(self.hiddenLayer.W ** 2).sum()
+ (self.logRegressionLayer.W ** 2).sum()
)
# negative log likelihood of the MLP is given by the negative
# log likelihood of the output of the model, computed in the
# logistic regression layer
self.negative_log_likelihood = (
self.logRegressionLayer.negative_log_likelihood
)
# same holds for the function computing the number of errors
self.errors = self.logRegressionLayer.errors
# the parameters of the model are the parameters of the two layer it is
# made out of
self.params = self.hiddenLayer.params + self.logRegressionLayer.params
# the cost we minimize during training is the negative log likelihood of
# the model plus the regularization terms (L1 and L2); cost is expressed
# here symbolically
cost = (
classifier.negative_log_likelihood(y)
+ L1_reg * classifier.L1
+ L2_reg * classifier.L2_sqr
)
# compute the gradient of cost with respect to theta (sorted in params)
# the resulting gradients will be stored in a list gparams
gparams = [T.grad(cost, param) for param in classifier.params]
# specify how to update the parameters of the model as a list of
# (variable, update expression) pairs
# given two lists of the same length, A = [a1, a2, a3, a4] and
# B = [b1, b2, b3, b4], zip generates a list C of same size, where each
# element is a pair formed from the two lists :
# C = [(a1, b1), (a2, b2), (a3, b3), (a4, b4)]
updates = [
(param, param - learning_rate * gparam)
for param, gparam in zip(classifier.params, gparams)
]
# compiling a Theano function `train_model` that returns the cost, but
# in the same time updates the parameter of the model based on the rules
# defined in `updates`
train_model = theano.function(
inputs=[index],
outputs=cost,
updates=updates,
givens={
x: train_set_x[index * batch_size: (index + 1) * batch_size],
y: train_set_y[index * batch_size: (index + 1) * batch_size]
}
)